Agent Claude Code
Implementation with full tool access except subagent delegation. Use when there is an approved plan and the work needs to land in code. Follows incremental-implementation, tests after each slice, self-checks with the review and security skills, and returns a gate-ready summary; the orchestrator runs the…
Agent Claude Code
Reviews a markdown draft for markdown formatting, clarity, structure, readability for its target reader (against the document plan when there is one), and voice. Returns OK or a list of issues. Read-only — flags, does not rewrite. Use proactively after drafting each major section of prose and before finalizing a…
Agent Claude Code
Verifies mathematical work with SymPy via Python one-liners. Returns formal verification result. Use proactively when the task involves mathematical derivations, formulas in decision models, or mechanism properties.
Agent Claude Code
Turns ideas into specs and implementation plans. Markdown only, no execution. Use proactively when starting a feature, when requirements are ambiguous, or when a change spans multiple files and no spec exists yet.
Agent Claude Code
Reviews a diff or code fragment with five-axis quality criteria. Returns OK or a list of issues with severity. Read-only — flags, does not fix. Use proactively immediately after writing or modifying code, before moving on.
Agent Claude Code
Reads a review thread and the surrounding document context, then proposes a reply or edit as a message.posted event with commit:null. Never edits the document body and never commits — the principal applies the proposal and creates the git commit. Use proactively when the principal fans out thread review tasks in…
Agent Claude Code
Security audit over diff, dependencies, or code fragment. Returns CLEAR or issues with CVSS and mitigation. Use proactively as a commit gate before committing security-sensitive changes (secrets, auth, input, deps, shell, network), not per-slice.
Command Claude Code
Initialize this workspace for the dotmesh agent system. Like /init but also wires shared skills and the AGENTS.md ↔ CLAUDE.md import.
Command Claude Code
Autonomously manage the Git lifecycle from sync and branch setup through atomic commits, push, and PR.
Hook Claude Code
One of 6 in settings.json
Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit, NotebookEdit and Skill tool calls, executing block-dangerous-git.sh, remind-review-gate.sh, remind-load-skills.sh and handoff-signal.sh (5 commands). From PabloCoello/dotmesh.
Hook Claude Code
One of 6 in settings.json
Runs when the agent finishes a response, executing close-review-gate.sh and verify-slice-commit.sh (2 commands). From PabloCoello/dotmesh.
Hook Claude Code
One of 6 in settings.json
Runs when a session starts, executing herdr-agent-state.sh and remind-herdr-skill.sh (2 commands). From PabloCoello/dotmesh.
Command Claude Code
Lanza review y security en paralelo sobre el último diff.
Command Claude Code
Snapshot estructurado del estado de trabajo.
Command Claude Code
Stop the current task and ask for one human decision before using more tools.
Skill Claude CodeCodex
Publish a claude.ai artifact page instead of a wall of terminal text when a maker-flow phase asks the user to read a lot or decide several things at once (grilling three or more independent closed questions, reviewing a spec longer than a screen, reporting measured results, following a long run phase by phase). The…
Hook Claude Code
One of 6 in settings.json
Runs after a tool call finishes for Artifact tool calls, executing offer-terminal-browser.sh. From PabloCoello/dotmesh.
Hook Claude Code
One of 6 in settings.json
Runs when a tool call fails for Bash tool calls, executing explain-sandbox-failure.sh. From PabloCoello/dotmesh.
Skill Claude CodeCodex
Plan a long document before drafting it, so it tells a story the reader can follow. Produces a template with the narrative arc, the target reader, a concept map (where each idea is introduced and at what depth), and a brief per section (purpose, new concepts, example, links in and out, recap). Load before drafting a…
Skill Claude CodeCodex
How to draft explanatory prose that carries the reader through the text instead of compressing meaning into as few words as possible. Covers writing for a reader who lacks the author's context, explanatory order inside a section, developing hard ideas over several sentences, making implicit links explicit (connectors…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: